3 papers
q-bio.NC2026
Platonic Representations in the Human Brain: Unsupervised Recovery of Universal Geometry
Pablo Marcos-Manchón, Rishi Jha, LluÃs Fuentemilla
The Strong Platonic Representation Hypothesis suggests that representational convergence in artificial neural networks can be harnessed constructively: embeddings can be translated…
q-bio.NC2026
Shared representations in brains and models reveal a two-route cortical organization during scene perception
Pablo Marcos-Manchón, LluÃs Fuentemilla
The brain transforms visual inputs into high-dimensional cortical representations that support diverse cognitive and behavioral goals. Characterizing how this information is organi…
cs.CV2024
Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models
Pablo Marcos-Manchón, Roberto Alcover-Couso, Juan C. SanMiguel +1
Diffusion models represent a new paradigm in text-to-image generation. Beyond generating high-quality images from text prompts, models such as Stable Diffusion have been successful…